initial_config-EQA2026.yaml

# THIS INITIAL CONFIG SHOULD BE SET AFTER INSTALLATION
# MAKE A COPY OF THIS FILE IN YOUR HOME AND CONFIGURE IT TO YOUR NEEDS
# THEN RUN: relecov-tools add-extra-config --config_file path/to/initial_config_copy.yaml
# IMPORTANT: Do not remove nor modify the required_conf keys unless you explicitly need to, that would surely break the code
# NOTE: Each key in 'modules_outpath' must match with a Command as listed with `relecov-tools --help` (but with '_' instead of '-')

# required_conf lists will be merged with the ones in configuration.json without override, keeping the sum of both
required_conf: ['generic', 'pipeline_manager', 'sftp_handle', 'read_lab_metadata', 'upload_to_gisaid', 'upload_to_ena', 'update_db', 'build_schema', 'download', 'logs_to_excel', 'mail_sender', 'map', 'metadata_homogeneizer', 'read_bioinfo_metadata', 'upload_results', 'validate', 'wrapper']

generic:
  required_conf: ["project_name", "json_schemas", "logs_config", "validate_config"]
  # Keep in mind that a required field missing or equal to "" will raise a validation error
  project_name: "EQA2026"
  logs_config:
    default_outpath: /tmp/
    modules_outpath:
      wrapper: /tmp/wrapper
      download: /tmp/download
      pipeline_manager: /tmp/pipeline_manager
      read_bioinfo_metadata: /tmp/read_bioinfo_metadata
  json_schemas:
    relecov_schema: relecov_schema_EQA.json
  validate_config:
    sample_id_ontology: "GENEPIO:0001123"

# CONFIG FOR MODULE PARAMETERS
mail_sender:
  required_conf: ["args"]
  # args can be used to set default values for the modules, can be overriden via CLI
  args:
    delivery_template_path_file: /path/templates/
    email_host: host
    email_port: port
    email_host_user: email@gmail.com
    email_use_tls: true
    yaml_cred_path: /path/credentials.yml
    institutions_guide_path: /path/contacts.json
download:
  required_conf: ["args"]
  args:
    user: ''
    password: ''
    conf_file: ''
    download_option: ''
    output_dir: ''
    target_folders: []
    subfolder: RELECOV
read_lab_metadata:
  required_conf: ["args", "unique_sample_id", "metadata_lab_heading_file", "alt_heading_equivalences", "lab_metadata_req_json", "samples_json_fields"]
  args:
    metadata_file: ''
    sample_list_file: ''
    output_dir: ''
    files_folder: ''
    cast_values_from_schema: true
    sample_data_map_field: collecting_lab_sample_id
    schema_file: relecov_schema_EQA.json
  metadata_lab_heading_file: read_lab_metadata_heading_default.json
  alt_heading_equivalences:
    Sample ID: Sample ID given for sequencing
    LAB ID: Originating Laboratory
    "Sequencing date Formato: YYYY-MM-DD": Sequencing Date
    Commercial All-in-one library kit: Commercial All-in-one library kit
    'Library preparation kit ': Library Preparation Kit
    Enrichment protocol: Enrichment Protocol
    if enrichment protocol is Other, specify: If Enrichment Protocol Is Other, Specify
    Amplicon protocol: Enrichment panel/assay
    if enrichment panel/assay is Other, specify: If Enrichment panel/assay Is Other, Specify
    Amplicon version: Enrichment panel/assay version
    Number Of Samples In Run: Number Of Samples In Run
    Number of variants with effect (missense, frameshit, stop codon): Number of variants with effect
    Sequencing platforms (Illumina, Nanopore, IonTorrent, PacBio, other): Sequencing Instrument Model
    Variant designation table filename: Lineage analysis file
    Library preparation kit: Library Preparation Kit
    Library layout: Library Layout
    Read lenght: Read length
    SARS-CoV-2 Lineage designation: Lineage designation
    fastq filename R1: Sequence file R1 fastq
    fastq filename R2: Sequence file R2 fastq
  lab_metadata_req_json: {}
  json_enrich:
    on_missing_schema_field: warn
  force_submitting_institution_id_from_lab_code: false
  required_copy_from_other_field: {}
  samples_json_fields:
  - sequence_file_R1_md5
  - sequence_file_R2_md5
  - sequence_file_R1
  - sequence_file_R2
  - sequence_file_path_R1
  - sequence_file_path_R2
  - batch_id

validate:
  required_conf: ["args"]
  args:
    json_file: ''
    json_schema_file: ''
    metadata: ''
    output_dir: ''
    excel_sheet: ''
    upload_files: false
    logsum_file: ''

map:
  required_conf: ["args"]
  args:
    destination_schema: ''
    json_file: ''
    origin_schema: ''
    output_dir: ''
    schema_file: ''

upload_to_ena:
  required_conf: ["args", "ENA_configuration", "checklist", "ena_fixed_fields", "additional_formating"]
  args:
    user: ''
    password: ''
    center: ''
    ena_json: ''
    template_path: ''
    action: ADD
    dev: false
    upload_fastq: false
    metadata_types: []
    output_dir: ''
  ENA_configuration:
    study_alias: RELECOV
    design_description: Design Description
    experiment_title: Project for ENA submission RELECOV
    study_title: RELECOV Spanish Network for genomics surveillance
    study_type: Whole Genome Sequencing
    study_id: ERP137164
    ena_broker_name: Instituto de Salud Carlos III
  checklist: ERC000033
  ena_fixed_fields:
    broker_name: Instituto de Salud Carlos III
    file_format: FASTQ
    study_alias: RELECOV
    study_title: RELECOV Spanish Network for genomics surveillance
    study_abstract: RELECOV is a Spanish Network for genomics surveillance
    insert_size: '0'
  additional_formating:
    sample_description:
    - host_common_name
    - anatomical_part
    - collection_method
    design_description:
    - library_layout
    - library_preparation_kit
    - library_selection
    - library_strategy
    sequence_file_path_R1:
    - sequence_file_path_R1
    - sequence_file_R1
    sequence_file_path_R2:
    - sequence_file_path_R2
    - sequence_file_R2
    experiment_alias:
    - isolate_sample_id
    - sample_collection_date
    run_alias:
    - isolate_sample_id
    - sample_collection_date
    experiment_title:
    - sequencing_instrument_model
    - isolate_sample_id
    file_name:
    - sequence_file_R1
    - sequence_file_R2
    file_checksum:
    - sequence_file_R1_md5
    - sequence_file_R2_md5

upload_to_gisaid:
  required_conf: ["args"]
  args:
    user: ''
    password: ''
    client_id: ''
    token: ''
    gisaid_json: ''
    input_path: ''
    output_dir: ''
    frameshift: ''
    proxy_config: ''
    single: false
    gzip: false
  GISAID_configuration:
    submitter: GISAID_ID

update_db:
  required_conf: ["args", "platform-params", "iskylims_fixed_values", "relecov_sample_metadata"]
  args:
    user: ''
    password: ''
    json: ''
    type: ''
    platform: ''
    server_url: ''
    full_update: false
    long_table: ''
  platform-params:
    iskylims:
      server_url: http://relecov-iskylims.isciiides.es
      api_url: /wetlab/api/
      store_samples: create-sample
      url_project_fields: projects-fields
      url_sample_fields: sample-fields
      param_sample_project: project
      project_name: relecov
      token: ''
    relecov:
      server_url: http://relecov-platform.isciiides.es
      api_url: /api/
      store_samples: createSampleData
      bioinfodata: createBioinfoData
      variantdata: createVariantData
      check_sample: checkSampleExists
      sftp_info: sftpInfo
      token: ''
  iskylims_fixed_values:
    patient_core: ''
    sample_project: Relecov
    only_recorded: 'Yes'
    sample_location: Not defined
  relecov_sample_metadata:
  - authors
  - collecting_institution
  - collecting_institution_code_1
  - collecting_lab_sample_id
  - ena_broker_name
  - ena_sample_accession
  - gisaid_accession_id
  - gisaid_virus_name
  - microbiology_lab_sample_id
  - sequence_file_path_R1
  - sequence_file_path_R2
  - schema_name
  - schema_version
  - sequencing_date
  - sequence_file_R1_md5
  - sequence_file_R2_md5
  - sequence_file_R1
  - sequence_file_R2
  - sequencing_sample_id
  - submitting_institution
  - submitting_lab_sample_id
  full_update_steps: [
    { "id": "1", "type": "sample", "platform": "iskylims" },
    { "id": "2", "type": "sample", "platform": "relecov" },
    { "id": "3", "type": "bioinfodata", "platform": "relecov" },
    { "id": "4", "type": "variantdata", "platform": "relecov" }
  ]

read_bioinfo_metadata:
  required_conf: ["args"]
  args:
    json_file: ''
    input_folder: ''
    output_dir: ''
    software_name: ''
    update: false

metadata_homogeneizer:
  required_conf: ["args"]
  args:
    institution: ''
    directory: ''
    output_dir: ''

pipeline_manager:
  required_conf: ["args", "analysis_group", "analysis_user", "organism_config"]
  args:
    input: ''
    templates_root: ''
    output_dir: ''
    folder_names: []
  analysis_group: RLV
  analysis_user: icasas_C
  organism_config:
    Severe acute respiratory syndrome coronavirus 2 [LOINC:LA31065-8]:
      pipeline_template: viralrecon
      service_tag: SARSCOV2
      group_by_fields:
      - sequencing_instrument_platform
      - enrichment_panel
      - enrichment_panel_version
    Respiratory syncytial virus [SNOMED:6415009]:
      pipeline_template: IRMA
      service_tag: GENOMERSV
      group_by_fields:
      - sequencing_instrument_platform
      - enrichment_panel
      - enrichment_panel_version
    Influenza virus [SNOMED:725894000]:
      pipeline_templates:
      - IRMA
      - taxprofiler
      service_tag: GENOMEFLU
      group_by_fields:
      - sequencing_instrument_platform

build_schema:
  required_conf: ["args"]
  args:
    input_file: ''
    schema_base: ''
    draft_version: ''
    diff: false
    version: ''
    project: ''
    non_interactive: false
    output_dir: ''

logs_to_excel:
  required_conf: ["args"]
  args:
    lab_code: ''
    output_dir: ''
    files: []

wrapper:
  required_conf: ["args"]
  args:
    output_dir: ''

upload_results:
  required_conf: ["args"]
  args:
    user: ''
    password: ''
    batch_id: ''
    template_path: ''
    project: Relecov

sftp_handle:
  required_conf: ["sftp_connection", "platform_storage_folder", "analysis_results_folder", "metadata_processing"]
  sftp_connection:
    sftp_server: sftpgenvigies.isciii.es
    sftp_port: '22'
  platform_storage_folder: /tmp/relecov
  analysis_results_folder: ANALYSIS_RESULTS
  metadata_processing:
    required_conf: ["header_flag", "excel_sheet", "sample_id_col"]
    header_flag: CAMPO
    excel_sheet: METADATA_LAB
    alternative_sheet: 5.Viral Characterisation and Se
    alternative_flag: CAMPO
    sample_id_col: Sample ID given by originating laboratory
    alternative_sample_id_col: Sample ID given by originating laboratory